Systems, devices and methods for non-invasive hematological measurements

Abstract

A system for non-invasive hematological measurements includes a platform to receive a body portion of a user and an imaging device to acquire a set of images of a capillary bed in the body portion. For each image, a controller detects one or more capillaries in the body portion of the finger to identify a first set of capillaries by estimating one or more attributes of each capillary (e.g., structural attributes, flow attributes, imaging attributes, or combinations thereof), wherein at least one attribute of each capillary meets a predetermined criterion. The controller also identifies a second set of capillaries from the first set of capillaries such that each capillary of the second set of capillaries is visible in a predetermined number of images of the set of images.

The invention claimed is: 
     
       1. A method of detecting neutropenia in a user, comprising:
 acquiring a set of images of a capillary bed of a body portion of the user; 
 detecting, without manual input, in one or more images of the set of images, one or more capillaries of the body portion; and 
 classifying the user to a first user type of a set of user types, at least one user type of the set of user types associated with a diagnosis of neutropenia, the classifying based on:
 an event count based on a set of cellular events in the one or more capillaries, each cellular event of the set of cellular events associated with passage of one or more types of white blood cells (WBCs) in a capillary of the one or more capillaries; and 
 an event count threshold associated with a minimum number of cellular events for classification of the user to the first user type, wherein the one or more capillaries comprises those capillaries having a diameter selected to be approximately equal to or less than a diameter of any WBC of the one or more types of WBCs for the user. 
 
 
     
     
       2. The method of  claim 1 , further comprising:
 receiving a set of training images associated with capillary beds in body portions of a set of training users; and 
 generating, via supervised learning, the event count threshold based on the set of training images. 
 
     
     
       3. The method of  claim 1 , further comprising:
 generating a confidence value associated with the image of each capillary of the one or more of capillaries in the set of images, the one or more capillaries including those capillaries for which the confidence value, for each image in which that capillary is detected, exceeds a confidence threshold. 
 
     
     
       4. The method of  claim 1 , the one or more capillaries including those capillaries having a diameter selected to be from about 10 μm to about 20 μm. 
     
     
       5. The method of  claim 1 , further comprising detecting each cellular event of the set of cellular events in its corresponding capillary by detecting, in the one or more images of the set of images corresponding to that capillary, an optical absorption gap during passage of the one or more types of WBCs in that capillary. 
     
     
       6. The method of  claim 5 , the detecting further comprising filtering each detected cellular event to remove, from the set of cellular events, that cellular event when that cellular event has a size outside a predetermined range of cellular event sizes. 
     
     
       7. The method of  claim 5 , the detecting further comprising filtering each detected cellular event to remove, from the set of cellular events, that cellular event when that cellular event has a relative absorption above a predetermined threshold. 
     
     
       8. The method of  claim 5 , the detecting further comprising filtering each detected cellular event to retain, in the set of cellular events, that cellular event when a temporal intensity profile associated with the detection of that cellular event exhibits a dip below an averaged intensity value for that temporal intensity profile at a time point that is subsequent to detection of that cellular event. 
     
     
       9. The method of  claim 5 , the detecting further comprising filtering each detected cellular event to remove, from the set of cellular events, when that cellular event is not moving in a predetermined direction in its corresponding capillary. 
     
     
       10. A device comprising processing circuitry, wherein the processing circuitry is configured to:
 acquire or receive a set of images of a capillary bed of a body portion of a user; 
 detect, without user input, in one or more images of the set of images, one or more capillaries of the body portion; and 
 classify the user to a first user type of a set of user types, at least one user type of the set of user types associated with a diagnosis of neutropenia, the classifying based on:
 an event count based on a set of cellular events in the one or more capillaries, each cellular event of the set of cellular events associated with passage of one or more types of white blood cells (WBCs) in a capillary of the one or more capillaries; and 
 an event count threshold associated with a minimum number of cellular events for classification of the user to the first user type, wherein the event count threshold is based on application of a supervised learning approach to a set of training images associated with capillary beds in body portions of a set of training users. 
 
 
     
     
       11. The device of  claim 10 , wherein the one or more capillaries comprises those capillaries having a diameter selected to be approximately equal to or less than a diameter of any WBC of the one or more types of WBCs for the user. 
     
     
       12. The device of  claim 10 , wherein the processing circuitry is further configured to detect each cellular event of the set of cellular events in its corresponding capillary by detecting, in the one or more images of the set of images corresponding to that capillary, an optical absorption gap during passage of the one or more types of WBCs in that capillary. 
     
     
       13. The device of  claim 12 , wherein the processing circuitry is further configured to filter each detected cellular event to remove, from the set of cellular events, that cellular event when that cellular event has a size outside a predetermined range of cellular event sizes. 
     
     
       14. The device of  claim 12 , wherein the processing circuitry is further configured to filter each detected cellular event to remove, from the set of cellular events, that cellular event when that cellular event has a relative absorption above a predetermined threshold. 
     
     
       15. The device of  claim 12 , wherein the processing circuitry is further configured to filter each detected cellular event to retain, in the set of cellular events, that cellular event when a temporal intensity profile associated with the detection of that cellular event exhibits a dip below an averaged intensity value for that temporal intensity profile at a time point that is subsequent to detection of that cellular event. 
     
     
       16. The device of  claim 12 , wherein the processing circuitry is further configured to filter each detected cellular event to remove, from the set of cellular events, when that cellular event is not moving in a predetermined direction in its corresponding capillary. 
     
     
       17. A system, comprising:
 an imaging device to acquire a set of images of at least a capillary bed of a body portion of a user during use; 
 a controller communicatively coupled to the imaging device, the controller configured to:
 acquire or receive a set of images of a capillary bed of a body portion of a user; 
 detect, without user input, in one or more images of the set of images, one or more capillaries of the body portion; and 
 classify the user to a first user type of a set of user types, at least one user type of the set of user types associated with a diagnosis of neutropenia, the classifying based on:
 an event count based on a set of cellular events in the one or more capillaries, each cellular event of the set of cellular events associated with passage of one or more types of white blood cells (WBCs) in a capillary of the one or more capillaries; and 
 an event count threshold associated with a minimum number of cellular events for classification of the user to the first user type. 
 
 
 
     
     
       18. The system of  claim 17 , wherein the controller is further configured to detect each cellular event of the set of cellular events in its corresponding capillary by detecting, in the one or more images of the set of images corresponding to that capillary, an optical absorption gap during passage of the one or more types of WBCs in that capillary,
 and wherein the controller is further configured to filter each detected cellular event to retain, in the set of cellular events, that cellular event when one or more of the following is true:
 that cellular event has a size within a predetermined range of cellular event sizes; 
 that cellular event has a relative absorption below a predetermined threshold; 
 a temporal intensity profile associated with the detection of that cellular event exhibits a dip below an averaged intensity value for that temporal intensity profile at a time point that is subsequent to detection of that cellular event; and 
 that cellular event is detected as moving in a predetermined direction in its corresponding capillary. 
 
 
     
     
       19. The system of  claim 17 , wherein the imaging device includes one or more of a camera, a smartphone including a camera, and a capillaroscope. 
     
     
       20. A method of detecting neutropenia in a subject, comprising:
 receiving a set of training images associated with capillary beds in body portions of a set of training users; and 
 generating, via supervised learning, an event count threshold based on the set of training images; 
 acquiring a set of images, with an imaging device, of a capillary bed of a body portion of the subject; 
 detecting, without manual input, in one or more images of the set of images, one or more capillaries of the body portion of the subject; 
 detecting a set of cellular events in the one or more capillaries; and 
 classifying the subject to a first classification type of a set of classification types, at least one classification type of the set of classification types associated with a diagnosis of neutropenia, the classifying based on:
 an event count based on the set of cellular events detected in the one or more capillaries, each cellular event of the set of cellular events associated with passage of one or more types of white blood cells (WBCs) in a capillary of the one or more capillaries; and 
 the event count threshold which is associated with a minimum number of cellular events for classification of the subject to the first classification type. 
 
 
     
     
       21. The method of  claim 20 , the one or more capillaries including those capillaries having a diameter selected to be from about 10 μm to about 20 μm. 
     
     
       22. The method of  claim 20 , further comprising filtering to exclude from the event count those detected cellular events of the set of cellular events having a size outside a predetermined range of cellular event sizes. 
     
     
       23. The method of  claim 20 , wherein the imaging device comprises at least one of a smartphone or a capillaroscope. 
     
     
       24. A method of detecting neutropenia in a subject, comprising:
 acquiring a set of images, with an imaging device, of a capillary bed of a body portion of the subject; 
 generating a confidence value associated with an image of each capillary of the one or more of capillaries in the set of images; 
 detecting, without manual input, in one or more images of the set of images, one or more capillaries of the body portion of the subject, the one or more capillaries including those capillaries for which the confidence value, for each image in which that capillary is detected, exceeds a confidence threshold; 
 detecting a set of cellular events in the one or more capillaries; and 
 classifying the subject to a first classification type of a set of classification types, at least one classification type of the set of classification types associated with a diagnosis of neutropenia, the classifying based on:
 an event count based on the set of cellular events detected in the one or more capillaries, each cellular event of the set of cellular events associated with passage of one or more types of white blood cells (WBCs) in a capillary of the one or more capillaries; and 
 the event count threshold which is associated with a minimum number of cellular events for classification of the subject to the first classification type. 
 
 
     
     
       25. The method of  claim 24 , the one or more capillaries including those capillaries having a diameter selected to be from about 10 μm to about 20 μm. 
     
     
       26. The method of  claim 24 , further comprising filtering to exclude from the event count those detected cellular events of the set of cellular events having a size outside a predetermined range of cellular event sizes. 
     
     
       27. The method of  claim 24 , wherein the imaging device comprises at least one of a smartphone or a capillaroscope.